vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: [ROCm][gfx1151] ROCM_ATTN returns different outputs for the same greedy request after other requests
- [Bugfix][KV Offload] Retain offload mappings after unsafe KVCR startup failure
- [MM][Mistral3] Image preprocessing optimization
- [Security] Bound FunAudioChat runtime audio to the profiled duration
- [Performance]: KV offload: DMA/Triton load threshold needs per-device profiling
- [Feature] Restore concurrent partial prefill limit (max_concurrent_prefills) in V1 scheduler
- [Bugfix][KV Offload] Unlink shared mmap by inode after all ranks map
- [Feature]: Production evidence for restoring concurrent partial prefill limits (max_num_partial_prefills / max_concurrent_prefills) in V1 scheduler
- feat: Add video support for the Transformers backend
- [ROCm][DI][CI] Swap container ionic RoCE userspace to a host-compatible AINIC channel
- Docs
- Python not yet supported